From 52092dc148693cb1e76a426c1e162ada582c9b77 Mon Sep 17 00:00:00 2001
From: Sebastian Wagner <sebix@sebix.at>
Date: Fri, 13 Sep 2024 07:48:05 +0200
Subject: [PATCH] markdown: stricter detection of embedded markup

instead of only checking only for the existence of `<`, check for text
directly behind the opening bracket and a closing bracket.

This prevents added paragraphs/new lines with just brackets or "arrows"
(`<-`) in lines.

fixes https://github.com/moinwiki/moin/issues/1761
---
 .../converters/_tests/test_markdown_in.py     | 21 +++++++++++++++++++
 src/moin/converters/markdown_in.py            |  3 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/src/moin/converters/_tests/test_markdown_in.py b/src/moin/converters/_tests/test_markdown_in.py
index 92b04c474..f0dd2d57e 100644
--- a/src/moin/converters/_tests/test_markdown_in.py
+++ b/src/moin/converters/_tests/test_markdown_in.py
@@ -182,6 +182,27 @@ def test_wikilinks(self, input, output):
     def test_admonition(self, input, output):
         self.do(input, output)
 
+    data = [
+        (
+            "one < two",
+            '<p>one &lt; two</p>',
+        ),
+        (
+            '[[one]] < two',
+            '<p><a xlink:href="wiki.local:one">one</a> &lt; two</p>',
+        ),
+        (
+            'pre <strong>bold</strong> post',
+            '<div><p>pre <strong>bold</strong> post</p></div>',
+        ),
+    ]
+
+    @pytest.mark.parametrize("input,output", data)
+    def test_embedded_markup(self, input, output):
+        """Test embedded markup in markdown"""
+        self.do(input, output)
+
+
     def serialize_strip(self, elem, **options):
         result = serialize(elem, namespaces=self.namespaces, **options)
         return self.output_re.sub("", result)
diff --git a/src/moin/converters/markdown_in.py b/src/moin/converters/markdown_in.py
index 7691c7c05..e2576d23c 100644
--- a/src/moin/converters/markdown_in.py
+++ b/src/moin/converters/markdown_in.py
@@ -531,7 +531,8 @@ def convert_embedded_markup(self, node):
         """
         for idx, child in enumerate(node):
             if isinstance(child, str):
-                if "<" in child:
+                # search for HTML tags
+                if re.search("<[^ ].*?>", child):
                     node[idx] = self.embedded_markup(child)  # child is immutable string, so must do node[idx]
             else:
                 # do not convert markup within a <pre> tag